US 11,806,579 B2
Sports operating system
William Ancil Brush, San Carlos, CA (US); Emily Jennifer Pye, Los Altos, CA (US); Shivay Lamba, Delhi (IN); Kieran Keegan, London (GB); Rahul Garg, Delhi (IN); John Peter Norair, San Francisco, CA (US); James P. Normile, III, Las Vegas, NV (US); and Jonathon G. Neville, Auckland (NZ)
Assigned to Sonador, Inc., Palo Alto, CA (US)
Filed by Sonador, Inc., Palo Alto, CA (US)
Filed on Sep. 16, 2021, as Appl. No. 17/477,425.
Application 17/477,425 is a continuation of application No. PCT/US2021/050543, filed on Sep. 15, 2021.
Claims priority of provisional application 63/079,424, filed on Sep. 16, 2020.
Prior Publication US 2022/0080263 A1, Mar. 17, 2022
Int. Cl. A63B 24/00 (2006.01); G06F 1/16 (2006.01); G06N 20/00 (2019.01); G06V 20/40 (2022.01)
CPC A63B 24/0062 (2013.01) [A63B 24/0006 (2013.01); G06F 1/163 (2013.01); G06N 20/00 (2019.01); G06V 20/42 (2022.01); G06V 20/46 (2022.01); A63B 2024/0009 (2013.01); A63B 2024/0068 (2013.01); A63B 2220/40 (2013.01); A63B 2220/806 (2013.01); A63B 2220/836 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for evaluating player metrics comprising, by one or more computing devices of a sports operating system:
accessing, by the one or more computing devices of the sports operating system, user sensor data from one or more wearable sensors on one or more players and optical sensor data from one or more cameras, wherein the user sensor data comprises location data of the player and acceleration data, and wherein the optical sensor data comprises a plurality of frames portraying the one or more players and a plurality of scenes from an athletic event;
analyzing, by a machine-learning model of the sports operating system, the optical sensor data to identify the one or more players associated with the one or more wearable sensors and one or more actions during the athletic event;
synchronizing, by the one or more computing devices of the sports operating system, the optical sensor data of the identified one or more players with user sensor data of the respective one or more wearable sensors on the identified one or more players using the analysis of the optical sensor data to identify the one or more players associated with the one or more wearable sensors and one or more actions during the athletic event;
calculating, by the one or more computing devices of the sports operating system, one or more player metrics for the identified one or more players based on the synchronized user sensor data and the identified actions captured within the synchronized optical sensor data, wherein the one or more player metrics are based on a role associated with the identified one or more players;
normalizing, using one or more benchmark algorithms of the sports operating system, the one or more player metrics for the one or more players based on one or more weighted parameters and one or more other player metrics corresponding to the one or more players having the same role associated with the identified one or more players;
predicting, using one or more performance evaluation algorithms of the sports operating system, one or more future outcome and one or more performance levels for the one or more players based on their associated roles; and
providing, by the one or more computing devices of the sports operating system, a report to one or more users about the one or more normalized player metrics and the one or more future outcomes and the one or more performance levels for the one or more players.